By Topic

Residuals modeling with wind data to improve short-term load forecast

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
S. Trento ; Dept. of Energy & Autom., Univ. of Sao Paulo, Sao Paulo, Brazil ; B. Delenne ; C. Crocombette

Short-term load forecasts are a major concern for transmission system operators. In France, RTE uses a parametric load model fed by temperature and cloud cover data. In this paper, we evaluate how the use of wind data may improve the quality of the model, both for fitting and forecasting. More precisely, the demand of Brittany, the peninsular area in the northwest of France is studied over the 2005-2010 period. Wind grid data that cover this area are supplied by the French public weather office Météo-France thanks to the ARPEGE numerical weather prediction model. The RTE load model residuals are successively modeled by four wind-related models (“rough wind model”, “smooth wind model”, “rough temperature wind model” and “smooth temperature wind model”). The results suggest that a significant gain can be achieved by post-processing load model residuals using wind data. The best model is the so-called “smooth temperature wind model”, which enables an overall significant 6.8% reduction of the root mean square error (RMSE) of operational day-ahead forecasts during the 2009/2010 winter season.

Published in:

PowerTech, 2011 IEEE Trondheim

Date of Conference:

19-23 June 2011